© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93363
    Prev
    Next
    INDEX
    Explanations

    data` parameter or structure initialization

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on code‐structuring tokens—especially punctuation and attribute‐binding syntax (colons, equals signs, braces, indentation markers, and component/attribute names) in HTML/JSX/Vue templates.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     if
    -1.26
    ッチリ
    -1.01
     tunik
    -0.96
     bazen
    -0.96
    lanan
    -0.96
    مقد
    -0.95
    ПРИ
    -0.94
    предели
    -0.94
    Salu
    -0.91
     bruises
    -0.90
    POSITIVE LOGITS
     doar
    1.01
    TIPOS
    0.88
     help
    0.86
     secondo
    0.86
     real
    0.86
     returns
    0.86
     Tenden
    0.85
     steuer
    0.85
    No
    0.85
     feel
    0.84
    Activations Density 0.001%

    No Known Activations